Method for Controlling the Number of Servers in a Hierarchical Resource Environment

1. A method for controlling the number of server instances in a computer system controlled by an operating system having server regions that are managed by a workload manager to provide resources for achieving service goals of work units received from application programs, said server regions including a number of server containers each containing a plurality of server instances operating in parallel to execute said work units received from said application programs, comprising the steps of: (a) sampling the server instances in a server container at execution time to obtain sample data representing resource usage of server instances that are active during a predetermined sampling interval, said sample data indicating resource contention among said server instances; (b) evaluating the sample data to determine a current resource consumption of the computer system in executing the work units; (c) (1) calculating an optimal number of server instances per server container from the current resource consumption of the computer system to execute the work units, said step comprising providing threshold values for current resource consumption and using said threshold values to permit or prevent an adjustment of the number of server instances in at least one of the server container, said step comprising restricting the number of server instances in each server container on the basis of restrictions on the total number of server instances permitted for all server containers executing work units for one or more server classes; (2) calculating an optimal total number of server instances, executing in parallel in each of the server containers, to execute the work units; (3) calculating a number of server containers from the optimal total number of server instances and from the optimal number of server instances per server container; and (d) providing feedback to the workload manager based upon the calculated number of server containers and the calculated number of server instances per server container, thereby to cause said workload manager to adjust the number of server containers and the number of server instances in at least one server container; and (e) repeating steps (a) to (d) at predetermined time intervals during execution of the work units.

2. The method of claim 1 in which the work units received from the application programs are assigned to service classes according to performance goals defined by the application programs, where at least some of the service classes have a hierarchical relationship to one another.

3. The method of claim 2 in which the work units of each service class are arranged in a work queue and one or more of said work queues contain the work units of one application program and are associated with one server container.

4. The method of claim 3 in which the number of server instances per server container for executing the work units is managed on the basis of both the service classes of the queued work units and the service classes of competing work in the computer system.

5. The method of claim 2 in which step (d) comprises the step of providing feedback to the workload manager for a server container of an upper level, and further comprises the step of adjusting the number of server containers based on the number of active server instances in each of the server containers.

6. The method of claim 1 in which the sample data represents the number of server instances that are active during a predetermined sampling interval.

7. The method of claim 1 in which step (b) comprises the step of determining available virtual storage space on the basis of the number of active server instances per server container.

8. The method of claim 1 in which step (b) comprises the step of determining available virtual storage space on the basis of the number of started server instances per server container.

9. The method of claim 1 in which step (b) comprises the step of determining local lock usage on the basis of the number of active server instances per server container.

10. A computer program product for controlling the number of server instances in a computer system controlled by an operating system having server regions that are managed by a workload manager to provide resources for achieving service goals of work units received from application programs, said server regions including a number of server containers each containing a plurality of server instances operating in parallel to execute said work units received from said application programs, the computer program product comprising program code means stored on a non-transitory computer readable medium that runs on a computer system to perform the following steps: (a) sampling the server instances in a server container at execution time to obtain sample data representing resource usage of server instances that are active during a predetermined sampling interval, said sample data indicating resource contention among said server instances; (b) evaluating the sample data to determine a current resource consumption of the computer system in executing the work units; (c) (1) calculating an optimal number of server instances per server container from the current resource consumption of the computer system, to execute the work units, said step comprising providing threshold values for current resource consumption and using threshold values to permit or prevent an adjustment of the number of server instances in at least one of the server containers, said step comprising restricting the number of server instances in each server container on the basis of restrictions on the total number of server instances permitted for all server containers executing work units for one or more server classes; (2) calculating an optimal total number of server instances, executing in parallel in each of the server containers, to execute the work units; (3) calculating a number of server containers from the optimal total number of server instances and from the optimal number of server instances per server container; and (d) providing feedback to the workload manager based upon the calculated number of server containers and the calculated number of server instances per server container, thereby to cause said workload manager to adjust the number of server containers and the number of server instances in at least one server; and (e) repeating steps (a) to (d) at predetermined time intervals during execution of the work units.

11. Apparatus for controlling the number of server instances in a computer system controlled by an operating system having server regions that are managed by a workload manager to provide resources for achieving service goals of work units received from application programs, said server regions including a number of server containers each containing a plurality of server instances operating in parallel to execute said work units received from said application programs, comprising: a hardware processor; (a) sampling the server instances in a server container at execution time to obtain sample data representing resource usage of server instances that are active during a predetermined sampling interval, said sample data indicating resource contention among said server instances; (b) evaluating the sample data to determine a current resource consumption of the computer system in executing the work units; (c) (1) calculating, via the hardware processor an optimal number of server instances per server container from the current resource consumption of the computer system to execute the work units, said step comprising providing threshold values for current resource consumption and using said threshold values to permit or prevent of the number of server instances in at least one of the server containers, said step comprising restricting number of server instances in each server container on the basis of restriction on the total number of server instances permitted for all server containers executing work units for one or more service class; (2) calculating an optimal total number of server instances, executing in parallel in each of the server containers, to execute the work units; (3) calculating a number of server containers from the optimal total number of server instances and from the optimal number of server instances per server container; and (d) providing feedback to the workload manager based upon the calculated number of server containers and the calculated number of server instances per server container, thereby to cause said workload manager to adjust the number of server containers and the number of server instances in at least one server; and (e) repeating steps (a) to (d) at predetermined time intervals during execution of the work units.